LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training

Abstract

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data override the trusted command and induce unintended behavior. Existing defenses mainly rely on fine-tuning the model to preserve an explicit boundary between trusted commands and the untrusted data portion, so that the model learns to prioritize the trusted field an

Categories

Framework mappings

Suggested from the entry's categories.

@misc{gong2026localalign,
  title = {{LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training}},
  author = {Yuyang Gong and Zihao Wang and Jiawei Liu and XiaoFeng Wang},
  year = {2026},
  month = may,
  eprint = {2605.01462},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.01462}
}